Real-Time Motion Planning for Agile Autonomous Vehicles

Frazzoli, Emilio; Dahleh, Munther A.; Féron, Éric

doi:10.2514/2.4856

Cited by 649 publications

(228 citation statements)

References 34 publications

Supporting

Mentioning

214

Contrasting

Unclassified

Order By: Relevance

“…Each time a sample is generated, m ≥ 1 attempts are made to connect a node to this sample before being discarded. Additional heuristics include attempting direct connections to the goal anytime a new node is added, and maintaining bounds on the cost-to-go to enable a branchand-bound pruning scheme (Frazzoli et al (2002)). …”

Section: Algorithm 4 Cc-rrt With Rr-gp Tree Expansionmentioning

confidence: 99%

“…The nearest node selection (lines 3-4) strategically alternates between several distance metrics for sorting the nodes, including an exploration metric based on cost-to-go and a path optimization metric based on estimated total path length (Frazzoli et al (2002)). Each time a sample is generated, m ≥ 1 attempts are made to connect a node to this sample before being discarded.…”

Section: Algorithm 4 Cc-rrt With Rr-gp Tree Expansionmentioning

confidence: 99%

See 1 more Smart Citation

Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patterns

et al. 2013

View full text Add to dashboard Cite

This paper presents a real-time path planning algorithm that guarantees probabilistic feasibility for autonomous robots with uncertain dynamics operating amidst one or more dynamic obstacles with uncertain motion patterns. Planning safe trajectories under such conditions requires both accurate prediction and proper integration of future obstacle behavior within the planner. Given that available observation data is limited, the motion model must provide generalizable predictions that satisfy dynamic and environmental constraints, a limitation of existing approaches. This work presents a novel solution, named RR-GP, which builds a learned motion pattern model by combining the flexibility of Gaussian processes (GP) with the efficiency of RRT-Reach, a sampling-based reachability computation. Obstacle trajectory GP predictions are conditioned on dynamically feasible paths identified from the reachability analysis, yielding more accurate predictions of future behavior. RR-GP predictions are integrated with a robust path planner, using chance-constrained RRT, to identify probabilistically feasible paths. Theoretical guarantees of probabilistic feasibility are shown for linear systems under Gaussian uncertainty; approximations for nonlinear dynamics and/or non-Gaussian uncertainty are also presented. Simulations demonstrate that, with this planner, an autonomous vehicle can safely navigate a complex environment in realtime while significantly reducing the risk of collisions with dynamic obstacles.

show abstract

Section: Algorithm 4 Cc-rrt With Rr-gp Tree Expansionmentioning

confidence: 99%

Section: Algorithm 4 Cc-rrt With Rr-gp Tree Expansionmentioning

confidence: 99%

Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patterns

et al. 2013

View full text Add to dashboard Cite

show abstract

“…RRTs have been used in several applications, and many variants have been developed [18,24,26,37,38,42,47,57,65,85,88,87,92,113,120,121,156,157,162,168,169]. Originally, they were developed for planning under differential constraints, but most of their applications to date have been for ordinary motion planning.…”

Section: Further Readingmentioning

confidence: 99%

Combinatorial Motion Planning

LaValle

2006

Planning Algorithms

View full text Add to dashboard Cite

“…For example, in [32] the authors present a motion planning algorithm which accounts for the computation time based on dynamic programming, while the work in [72] uses a mixed integer linear programming receding horizon approach to the same effect. We can safely conclude that the single-agent motion planning problem is reasonably well understood.…”

Section: Multi-agent Systemsmentioning

confidence: 99%